poll_trialPoll a trial watch created by try_watch. Free. Pass since={last seq you saw}; the response carries a new cursor. Once the trial expires, create a paid watch with create_watch; paid creation includes 7 days of polling and can be renewed. Free — no payment required.
| Name | Required | Description | Default |
|---|---|---|---|
| key | Yes | key returned by try_watch | |
| since | No | highest alert seq already seen; 0 on first poll | |
| watch_id | Yes | watch_id returned by try_watch |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses that the tool is free and that the response carries a new cursor, which is useful. However, it does not disclose authentication needs, error behavior when the trial has expired, or whether the operation has any side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The first sentence is well front-loaded and the lifecycle guidance is useful, but the description repeats the same cost point twice: 'Free.' and 'Free — no payment required.' This redundancy weakens an otherwise compact description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple polling tool with complete schema coverage, it covers the cursor contract, trial expiration path, and cost. Since there is no output schema, it at least indicates the response carries a new cursor, though it does not describe the alert payload itself.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the baseline is 3. The description adds real semantic value by defining since as the last sequence number seen and stating the response returns a new cursor, which clarifies the continuation pattern beyond the raw schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Uses a specific verb 'Poll' plus a specific resource, 'trial watch created by try_watch', which clearly separates it from siblings like create_watch, delete_watch, and poll_alerts. The title reinforces the same resource without mere tautology.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explains when to use the tool: pass since={last seq seen} while polling a trial watch, and explicitly points to create_watch once the trial expires, including the 7-day paid polling renewal detail. It does not explicitly contrast with poll_alerts for paid watches, so it stops short of a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools are clearly separated into immediate check_* and persistent watch_* counterparts across distinct source types, plus lifecycle tools for creating, polling, and deleting watches. The generic check_now and create_watch overlap somewhat with the specialized check_*/watch_* tools, but the descriptions clarify session vs. persistent usage.
The check_<source>/watch_<source> pairing is consistent across all six monitored source types, and lifecycle tools use predictable verb-based names like create_watch, delete_watch, poll_alerts, and try_watch. Minor deviations like check_now and create_watch rather than watch_create break the pattern slightly, but the overall convention remains legible.
Eighteen tools is on the heavier side, but the count is justified by six source types each having both a check and watch mode, plus lifecycle operations. The generic check_now and create_watch add redundancy with the specialized tools, making the set slightly larger than strictly necessary.
The server covers immediate checks, persistent watches, trial watches, polling, and deletion, so the main monitoring workflow is present. However, there is no update_watch, list_watches, or get_watch status tool, so agents cannot modify or enumerate existing watches and must delete/recreate instead.